Debian Codegraph @

recipes/nypost.recipe

raw
1 #!/usr/bin/env python
2 # vim:fileencoding=utf-8
3 from calibre.web.feeds.news import BasicNewsRecipe, classes
4
5
6 class NewYorkPost(BasicNewsRecipe):
7 title = 'New York Post'
8 __author__ = 'unkn0wn'
9 description = 'Daily newspaper'
10 publisher = 'NYP Holdings, Inc.'
11 category = 'news, politics, USA'
12 oldest_article = 1
13 no_stylesheets = True
14 encoding = 'utf-8'
15 use_embedded_content = False
16 language = 'en_US'
17 remove_attributes = ['style', 'height', 'width']
18 masthead_url = 'https://static.storied.co/gQlwL7PA4X5XM6b8/projects/JYX3m27B8zP9BW4D/assets/images/81e851fd6c5d8fc747c41064d8aee316.png'
19 extra_css = '.byline, .date, .article-header__top, .calibre-nuked-tag-figcaption { font-size: small; }'
20
21 def get_cover_url(self):
22 soup = self.index_to_soup('https://www.frontpages.com/us-newspapers/')
23 for img in soup.findAll('img', src=True):
24 if 'new-york-post' in img['src']:
25 return 'https://www.frontpages.com' + img['src']
26
27 recipe_specific_options = {
28 'days': {
29 'short': 'Oldest article to download from this news source. In days ',
30 'long': 'For example, 0.5, gives you articles from the past 12 hours',
31 'default': str(oldest_article),
32 }
33 }
34
35 def __init__(self, *args, **kwargs):
36 BasicNewsRecipe.__init__(self, *args, **kwargs)
37 d = self.recipe_specific_options.get('days')
38 if d and isinstance(d, str):
39 self.oldest_article = float(d)
40
41 ignore_duplicate_articles = {'title', 'url'}
42
43 keep_only_tags = [
44 classes('article-header single__content'),
45 ]
46
47 remove_tags = [
48 dict(attrs={'id': ['connatix-outstream-video']}),
49 classes('article-header__social-icons wpcom-liveblog-container nyp-s2n-wrapper nyp-slideshow-modal-image__icon inline-module inline-module__inner'),
50 dict(name=['svg', 'link', 'meta', 'aside']),
51 ]
52
53 # https://nypost.com/rssfeeds/
54 feeds = [
55 ('US-News', 'https://nypost.com/us-news/feed/'),
56 ('Metro', 'https://nypost.com/metro/feed/'),
57 ('Politics', 'https://nypost.com/politics/feed/'),
58 ('World News', 'https://nypost.com/world-news/feed/'),
59 ('Sports', 'https://nypost.com/sports/feed/'),
60 ('Business', 'https://nypost.com/business/feed/'),
61 ('Opinion', 'https://nypost.com/opinion/feed/'),
62 ('Entertainment', 'https://nypost.com/entertainment/feed/'),
63 ('Fashion & Beauty', 'https://nypost.com/fashion-and-beauty/feed/'),
64 ('Lifestyle', 'https://nypost.com/lifestyle/feed/'),
65 ('Tech', 'https://nypost.com/tech/feed/'),
66 ('Media', 'https://nypost.com/media/feed/'),
67 ('Real Estate', 'https://nypost.com/real-estate/feed/'),
68 ('Page Six', 'https://pagesix.com/feed/'),
69 ('Others', 'https://nypost.com/feed/'),
70 ]
71
72 def preprocess_html(self, soup):
73 for img in soup.findAll('img', attrs={'src': True}):
74 img['src'] = img['src'].split('?')[0] + '?w=600'
75 return soup